Traces

Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.

Flight-Sim Renderer in OpenGL

task page →110 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GPT-6 Astra0.9965$2541.331210.9M2.5M19h 50m283027
2GPT-6 Astra0.9845$2685.881278.3M2.6M20h 0m296138
3GPT-6 Astra0.9844$2735.711297.4M2.6M19h 42m288429
4GPT-6 Astra0.9841$2589.721228.2M2.6M19h 59m280134
5GPT-6 Astra0.9841$2728.191288.8M2.7M19h 57m294147
6Gemini 4 Argon0.9334$206.78382.0M1.3M15h 47m8775
7Claude Opus 5.50.9097$156.04545.9M1.3M19h 52m128819
8Claude Sonnet 5.50.9083$181.73740.0M2.3M18h 47m15466
9Gemini 4 Argon0.9080$207.90379.4M1.5M15h 34m85410
10Claude Sonnet 5.50.8981$169.21677.4M2.4M19h 40m15494
11Claude Opus 5.50.8821$144.22511.3M1.0M18h 11m107426
12Claude Opus 5.50.8618$140.79553.3M1.1M19h 44m11914
13Claude Opus 5.50.8540$182.36671.0M1.3M19h 5m163723
14Gemini 4 Argon0.8458$261.90442.3M1.8M19h 2m10566
15Claude Sonnet 5.50.7941$169.89694.5M2.3M19h 11m15802
16Gemini 4 Argon0.7148$130.35185.9M816k8h 32m4493
17Gemini 4 Argon0.7072$170.81258.5M1.2M8h 45m6733
18Claude Sonnet 5.50.7057$164.69656.9M2.0M19h 44m15666
19Claude Sonnet 5.50.6877$201.48823.9M2.7M19h 38m18978
20Claude Opus 5.50.6632$158.77603.5M1.1M18h 8m12037
21Claude Fable 5.10.4716$208.91376.5M866k17h 50m101710
22Claude Fable 5.10.3532$168.41314.0M539k12h 53m6084
23Claude Fable 5.10.3481$106.70193.6M429k9h 8m45413
24Claude Fable 5.10.3402$125.75229.9M473k10h 25m4826
25Claude Opus 50.2471$159.25261.3M595k19h 14m5303
26GPT-5.6 Sol0.2171$270.86274.0M362k12h 30m8064
27Claude Haiku 5.50.2045$31.05511.9M1.8M18h 49m11383
28Claude Opus 50.2039$238.32344.9M699k19h 25m73512
29Claude Fable 5.10.1985$113.40205.2M463k5h 28m4303
30Claude Fable 50.1934$427.55353.3M996k18h 35m9243
31Claude Haiku 5.50.1872$31.43521.7M1.9M17h 21m11525
32Claude Opus 50.1567$190.60308.2M776k19h 30m7425
33GPT-5.6 Sol0.1552$336.67340.6M347k11h 28m90614
34Claude Fable 50.1550$396.50323.2M982k19h 5m8487
35Grok 4.70.1336$487.10480.1M1.3M20h 1m183777
36Claude Fable 50.1319$351.84291.9M807k19h 38m7118
37Claude Opus 50.1302$226.32342.2M722k19h 35m76014
38GPT-5.6 Sol0.1222$253.61257.1M305k8h 28m7603
39Grok 4.70.1182$509.72506.8M1.5M18h 52m206885
40Grok 4.70.1138$588.60597.8M1.8M19h 55m2409106
41GPT-5.6 Sol0.1119$309.74312.3M342k9h 22m85712
42Muse Spark 1.30.1055$206.91689.2M886k10h 35m16811
43GPT-5.6 Sol0.1032$420.32406.2M354k11h 35m88013
44Claude Fable 50.0950$314.88250.5M673k18h 55m4847
45Claude Haiku 5.50.0884$18.09294.8M1.2M8h 15m6824
46Claude Haiku 5.50.0726$19.59319.7M1.3M12h 4m7105
47Grok 4.70.0713$540.56547.5M1.5M19h 14m2247102
48Grok 4.60.0526$317.62274.4M1.8M19h 55m1078110
49Muse Spark 1.30.0410$299.15649.2M932k19h 37m15882
50Muse Spark 1.30.0386$233.75628.1M517k18h 2m12825
51Grok 4.60.0382$286.38260.8M1.4M19h 57m984103
52Gemini 3.8 Flash0.0349$41.18386.0M562k10h 22m9704
53Grok 4.60.0273$488.84437.7M2.0M19h 56m1536307
54Grok 4.60.0266$454.46403.4M2.0M19h 58m143575
55Muse Spark 1.30.0254$147.68673.6M1.0M19h 47m15618
56Muse Spark 1.30.0250$351.72511.0M807k19h 59m13001
57Kimi K30.0249$126.07350.4M1.1M19h 56m9367
58Claude Opus 50.0249$181.57297.4M666k19h 31m6026
59Kimi K30.0214$168.60476.4M1.3M20h 1m10795
60Grok 4.70.0196$518.13515.0M1.7M19h 40m207958
61GLM-5.30.0166$91.30316.9M852k19h 35m8917
62Grok 4.60.0147$328.36283.8M1.8M19h 57m108457
63Claude Haiku 5.50.0140$10.65174.9M638k2h 59m3515
64Gemini 3.8 Flash0.0130$23.89196.2M401k6h 33m5073
65Gemini 3.7 Flash0.0116$11.2868.7M237k4h 7m3042
66Kimi K30.0104$167.00460.9M1.4M20h 1m10391
67Gemini 3.8 Flash0.0089$32.30275.0M453k6h 8m6104
68Kimi K30.0079$184.18516.4M1.3M19h 37m10942
69DeepSeek V4 Flash Vision Exp0.0069$10.96663.9M1.1M19h 2m15272
70DeepSeek V4 Flash Vision Exp0.0065$10.60633.4M1.1M15h 56m15168
71Gemini 3.7 Flash0.0064$35.75195.3M360k8h 28m5551
72GLM-5.30.0054$111.06362.5M755k19h 29m89310
73Gemini 3.7 Flash0.0054$6.5251.3M224k2h 40m2742
74GLM-5.30.0038$97.66297.0M573k19h 4m6335
75DeepSeek V4 Flash Vision Exp0.0028$12.40756.6M1.2M19h 8m175639
76DeepSeek V4 Flash Vision Exp0.0027$6.77415.2M638k18h 28m8377
77Gemini 3.7 Flash0.0020$17.05105.9M300k5h 32m3811
78Qwen3.8-Max0.0018$183.02558.1M1.7M19h 56m13751
79Qwen3.8-Max0.0016$153.43448.8M1.7M19h 59m12021
80GLM-5.3 Flash0.0015$14.67306.8M449k20h 1m7461
81Qwen3.8-Max0.0010$149.46419.0M1.2M19h 25m9932
82GLM-5.3 Flash0.0010$16.55339.1M548k17h 44m7405
83Gemini 3.7 Flash0.0009$11.2877.4M230k5h 1m3693
84Gemini 3.8 Flash0.0007$23.00212.3M376k5h 7m5263
85GLM-5.30.0006$94.18300.9M621k18h 57m59210
86GLM-5.3 Flash0.0002$12.16275.0M487k19h 36m6283
87GLM-5.3 Flash0.0001$17.12399.9M616k15h 49m8285
88Qwen3.8-Max0.0001$169.64519.3M1.6M20h 0m12391
89Muse Spark 1.20.0000$7.7740.8M287k2h 9m1825
90Inkling0.0000$6.727.0M25k22m1382
91Qwen3.8-Max0.0000$189.91559.5M1.9M19h 51m14643
92Kimi K30.0000$182.81498.0M1.4M20h 1m10632
93Muse Spark 1.20.0000$8.0738.9M412k3h 7m2024
94DeepSeek V4 Flash Vision Exp0.0000$11.01666.7M1.1M19h 11m146711
95Qwen3.8-Max-09020.0000$58.14147.3M957k20h 6m4341
96Qwen3.8-Max-09020.0000$33.94103.0M952k20h 7m3671
97Muse Spark 1.20.0000$6.3024.2M135k1h 37m1594
98Qwen3.8-Max-09020.0000$41.8596.9M886k20h 4m4141
99Claude Fable 50.0000$411.65293.0M731k19h 45m6983
100GLM-5.30.0000$103.09375.1M554k19h 46m79012
101Gemini 3.8 Flash0.0000$53.67394.0M628k13h 26m10684
102Inkling0.0000$6.596.8M31k2h 10m1462
103Muse Spark 1.20.0000†$2.6412.4M42k2h 25m902
104Qwen3.8-Max-09020.0000$50.29127.1M914k20h 7m4791
105Inkling0.0000$6.576.8M31k35m1561
106GLM-5.3 Flash0.0000$17.57389.3M753k20h 0m8918
107Qwen3.8-Max-09020.0000$56.38146.6M1.2M20h 0m4681
108Inkling0.0000$4.244.4M17k41m1091
109Inkling0.0000$8.879.2M43k1h 49m1702
110Muse Spark 1.20.0000†$1.728.1M39k1h 17m881

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.